Assume that you have an existing trained reinforcement learning agent. For this example, load the trained agent fromTrain DDPG Agent to Control Double Integrator System.

load('DoubleIntegDDPG.mat','agent')

Obtain the critic function approximator from the agent.

critic = getCritic(agent);

Obtain the learnable parameters from the critic.

params = getLearnableParameters(critic)

params=2×1 cell array{[-5.0077 -1.5619 -0.3475 -0.0961 -0.0455 -0.0026]} {[ 0]}

Modify the parameter values. For this example, simply multiply all of the parameters by2.

modifiedParams = cellfun(@(x) x*2,params,'UniformOutput',false);

Set the parameter values of the critic to the new modified values.

critic = setLearnableParameters(critic,modifiedParams);

Set the critic in the agent to the new modified critic.

setCritic(agent,critic);

Display the new parameter values.

getLearnableParameters(getCritic(agent))

ans =2×1 cell array{[-10.0154 -3.1238 -0.6950 -0.1922 -0.0911 -0.0052]} {[ 0]}

Create an environment with a continuous action space and obtain its observation and action specifications. For this example, load the environment used in the exampleTrain DDPG Agent to Control Double Integrator System.

Load the predefined environment.

env = rlPredefinedEnv("DoubleIntegrator-Continuous");

Obtain observation and action specifications.

obsInfo = getObservationInfo(env); actInfo = getActionInfo(env);

Create a PPO agent from the environment observation and action specifications. This agent uses default deep neural networks for its actor and critic.

agent = rlPPOAgent(obsInfo,actInfo);

To modify the deep neural networks within a reinforcement learning agent, you must first extract the actor and critic function approximators.

actor = getActor(agent); critic = getCritic(agent);

Extract the deep neural networks from both the actor and critic function approximators.

actorNet = getModel(actor); criticNet = getModel(critic);

The networks aredlnetwork对象. To view them using theplotfunction, you must convert them tolayerGraph对象.

For example, view the actor network.

plot(layerGraph(actorNet))

To validate a network, useanalyzeNetwork. For example, validate the critic network.

analyzeNetwork(criticNet)

You can modify the actor and critic networks and save them back to the agent. To modify the networks, you can use theDeep Network Designerapp. To open the app for each network, use the following commands.

deepNetworkDesigner(layerGraph(criticNet)) deepNetworkDesigner(layerGraph(actorNet))

InDeep Network Designer, modify the networks. For example, you can add additional layers to your network. When you modify the networks, do not change the input and output layers of the networks returned bygetModel. For more information on building networks, seeBuild Networks with Deep Network Designer.

To validate the modified network inDeep Network Designer, you must click onAnalyze for dlnetwork, under theAnalysissection. To export the modified network structures to the MATLAB® workspace, generate code for creating the new networks and run this code from the command line. Do not use the exporting option inDeep Network Designer. For an example that shows how to generate and run code, seeCreate Agent Using Deep Network Designer and Train Using Image Observations.

For this example, the code for creating the modified actor and critic networks is in thecreateModifiedNetworkshelper script.

createModifiedNetworks

Each of the modified networks includes an additionalfullyConnectedLayerandreluLayerin their main common path. View the modified actor network.

plot(layerGraph(modifiedActorNet))

After exporting the networks, insert the networks into the actor and critic function approximators.

actor = setModel(actor,modifiedActorNet); critic = setModel(critic,modifiedCriticNet);

Finally, insert the modified actor and critic function approximators into the actor and critic objects.

agent = setActor(agent,actor); agent = setCritic(agent,critic);